Overview
Qwen3.6 Flash is a latency-optimized member of the Qwen3.6 lineup. It offers tiered pricing across a 256K context boundary and supports explicit cache to dramatically cut cost on repeated prefixes — accessible through MuleRouter via the OpenAI-compatible Chat Completions endpoint.
Key Features
- Tiered pricing — $0.25 input / $1.5 output under 256K; scales to $1 / $4 between 256K and 1M
- Explicit cache support — Cache hit at 10% of input price; cache creation at 125% of input price
- OpenAI-compatible API — Use the standard
/vendors/openai/v1/chat/completions endpoint
- Streaming support — Real-time token streaming for responsive applications
Usage
Set model to qwen3.6-flash in your request body. All standard OpenAI chat completion parameters are supported.
Pricing
Per Million Tokens
0 < Tokens <= 256K
Input Price: $0.25
Cached Input: $0.025
Output Price: $1.5
256K < Tokens <= 1M
Input Price: $1
Cached Input: $0.1
Output Price: $4